Title :
Automatic Image Processing Filter Creation System Using NN
Author :
Hata, Seiji ; Tanaka, Takateru ; Iga, Teppei ; Nakamura, Takashi
Author_Institution :
Kagawa Univ., Kagawa
Abstract :
The visual inspection system is used in various production systems. The visual inspection system judges the quality of products. But, there are some defects which are not detected with enough reliability on conventional systems. Therefore, the automatic generation system of best image processing filters which extract the proper characteristics of images for that kind of defects is proposed to improve recognition rate. This system is designed to generate the filters to detect the defects with vague edge precisely using neural network. Experiments shows the generated filters get better recognition rate.
Keywords :
automatic optical inspection; computerised instrumentation; filters; image recognition; neural nets; production engineering computing; automatic generation system; automatic image processing filter creation; defect detection; neural network; visual inspection system; Character recognition; Computer vision; Filters; Image edge detection; Image processing; Image recognition; Inspection; Neural networks; Printing; Production systems;
Conference_Titel :
Industrial Electronics, 2007. ISIE 2007. IEEE International Symposium on
Conference_Location :
Vigo
Print_ISBN :
978-1-4244-0754-5
Electronic_ISBN :
978-1-4244-0755-2
DOI :
10.1109/ISIE.2007.4374837
